Identifying Stage II Colorectal Cancer Recurrence Associated Genes by Microarray Meta-Analysis and Building Predictive Models with Machine Learning Algorithms

Abstract

Background. Stage II colorectal cancer patients had heterogeneous prognosis, and patients with recurrent events had poor survival. In this study, we aimed to identify stage II colorectal cancer recurrence associated genes by microarray meta-analysis and build predictive models to stratify patients’ recurrence-free survival. Methods. We searched the GEO database to retrieve eligible microarray datasets. The microarray meta-analysis was used to identify universal recurrence associated genes. Total samples were randomly divided into the training set and the test set. Two survival models (lasso Cox model and random survival forest model) were trained in the training set, and AUC values of the time-dependent receiver operating characteristic (ROC) curves were calculated. Survival analysis was performed to determine whether there was significant difference between the predicted high and low risk groups in the test set. Results. Six datasets containing 651 stage II colorectal cancer patients were included in this study. The microarray meta-analysis identified 479 recurrence associated genes. KEGG and GO enrichment analysis showed that G protein-coupled glutamate receptor binding and Hedgehog signaling were significantly enriched. AUC values of the lasso Cox model and the random survival forest model were 0.815 and 0.993 at 60 months, respectively. In addition, the random survival forest model demonstrated that the effects of gene expression on the recurrence-free survival probability were nonlinear. According to the risk scores computed by the random survival forest model, the high risk group had significantly higher recurrence risk than the low risk group (HR = 1.824, 95% CI: 1.079–3.084, p = 0.025). Conclusions. We identified 479 stage II colorectal cancer recurrence associated genes by microarray meta-analysis. The random survival forest model which was based on the recurrence associated gene signature could strongly predict the recurrence risk of stage II colorectal cancer patients.

Prediction of University Patent Transfer Cycle Based on Random Survival Forest

“…Based on the existing representative literatures [18][19][20][21][22], it is considered that the Cox proportional risk model [23], Cox proportional risk model with penalty [24], random forest model based on machine learning [25], and random survival forest model [26] are popular in survival analysis research. In addition, since previous studies have shown that the lasso method can obtain better prediction results than the forward and the backward stepwise regression methods [27], the lasso method is adopted to establish a proportional risk model with penalty in this paper.…”